Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add nutriandrea/adobe-indesign-mcp --skill indesign-layoutgit clone --depth 1 https://github.com/nutriandrea/adobe-indesign-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nutriandrea/adobe-indesign-mcp/indesign-layout)<a href="https://agentmods.dev/skills/nutriandrea/adobe-indesign-mcp/indesign-layout"><img src="https://agentmods.dev/badge/skills/nutriandrea/adobe-indesign-mcp/indesign-layout/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nutriandrea/adobe-indesign-mcp/indesign-layout"><img src="https://agentmods.dev/badge/skills/nutriandrea/adobe-indesign-mcp/indesign-layout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00132 | $0.02421 |
| Opus 5.5 | $0.00053 | $0.00968 |
| Sonnet 5.5 | $0.00026 | $0.00484 |
| Haiku 4.5 | $0.00013 | $0.00242 |
Grade A, and why
indesign-layout scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Layout in Adobe InDesign
Drives a running Adobe InDesign through the indesign-nutria-mcp server, whose
197 tools — typed, validated and grouped by object — cover documents, pages,
text, styles, tables, colour, images, masters, footnotes, cross-references,
tables of contents, indexes, data merge, books and export.
Reach for this skill when the user wants work done in InDesign: building or editing a layout, placing a manuscript, typesetting, preparing a press-ready PDF, or automating a folder of documents.
InDesign has no headless mode. Everything here drives the application the user has open, so "just render it in CI" is not an option — and the skill should say so rather than pretend otherwise.
Before the first call
Setup (installing the server, wiring the host, opening the bridge) is in
SETUP.md, shipped next to this file.
Three things must be true before any tool works:
- InDesign is open. Most tools act on an open document; with none open they fail. On the Windows COM bridge the instance must also be visible, otherwise the user is looking at an empty application.
- One bridge is running — the UXP panel,
./start-bridge.sh, or the COM bridge on Windows. Sending a raw script to InDesign has no cancellation: if it hangs, the host stays busy and every later call queues behind it. - The connection is checked once.
document_listOpenis the cheap probe: if it returns a document list, the whole path works. If a call fails withbridge_not_connected, stop and tell the user to open InDesign and the bridge. Do not retry in a loop — the bridge cannot appear on its own.
The contract
This server does not just expose tools, it expects to be driven a certain way. Each rule below prevents a specific, common failure.
- Use the typed tools. They validate arguments, wrap ExtendScript and apply
timeouts.
export_executeScriptandscript_runpush code straight to the bridge with no cancellation — never use them for loops, font enumeration, multi-object probes, or anything touching many DOM objects. - State before action. Call
document_getStatebefore mutating: it returns the front document's geometry, the other open documents, the active layer and the selection in one round-trip. Do not assume geometry. - Target the document explicitly. Every tool takes
document_id— a document name (asdocument_listOpenreports it) or a 0-based index. Without it a tool acts on the front document, so with several open, passdocument_idrather than trusting the front tab. - Read errors as data. A failed call returns
{ ok: false, code, message, suggested_next_tool? }. Act onsuggested_next_toolinstead of guessing. - Group multi-step edits. Wrap a multi-step call in
undo_beginGroup/undo_endGroupso the whole call is one undo step. - Look at what you made. Call
preview_documentbefore reporting success rather than assuming the change landed. - Never leave a dialog possible.
document_closedefaults tosaveOptions: "no", which cannot prompt. Calldocument_savefirst when the work should be kept, and never pass"ask"while acting unattended — a modal save dialog blocks the script until the bridge times out.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 189 lines · 132 tokens per session scan A b54e2ea1d85b
indesign-layout is a skill published in the GitHub repository nutriandrea/adobe-indesign-mcp (34 stars, last pushed 2d ago), licensed MIT. It adds 132 tokens to every session and 2,421 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-20.
Other skills, from other repositories
adobe-design-to-pdf
Find an Adobe Express template, customize its text or background color, and turn it into a print-ready PDF, packet, or shareable link. Use whenever the user asks to make a flyer, poster, banner, brochure, sign, or other print piece and mentions PDF, printing, a packet, or sharing — for example, “make me a flyer and…
kami
A design and typesetting guide for creating professional documents and product landing pages, such as resumes, white papers, portfolios, and slide decks.
adobe-document-review
Smart highlighter for any PDF — contracts, invoices, medical records, manuals, resumes, reports, prose. For broad requests, offers a review-focus menu (what matters most, risks/obligations, key dates & figures, or custom), classifies the document, and highlights accordingly with comments on most focuses. Use for broad…
adobe-anypdf
MANDATORY: any PDF task (.pdf file, 'PDF', compress/shrink/reduce size, merge, split, extract/rotate/reorder/delete pages, OCR, redact, highlight, annotate, sign, fill forms, convert to/from PDF, page count/metadata/password) requires viewing THIS file, not just the public 'pdf' skill. Seeing 'pdf' in the built-in…
solidworks-engineering-drawing
A SolidWorks skill for creating and reviewing engineering drawings, which are manufacturing documents showing views, measurements, holes, parts lists, and title-block information.
azure-ai-document-intelligence-ts
Extract text, tables, and structured data from documents using Azure Document Intelligence (@azure-rest/ai-document-intelligence). Use when processing invoices, receipts, IDs, forms, or building cu...